> Explainable AI (XAI), or Interpretable AI, or Explainable Machine Learning (XML), [1] is artificial intelligence (AI) in which humans can understand the decisions or predictions made by the AI. [2] It contrasts with the "black box" concept in machine learning where even its designers cannot explain why an AI arrived at a specific decision. [3][4] By refining the mental models of users of AI-powered systems and dismantling their misconceptions, XAI promises to help users perform more effectively. [5] XAI may be an implementation of the social _ right to explanation _. [6] XAI is relevant even if there is no legal right or regulatory requirement. For example, XAI can improve the user experience of a product or service by helping end users trust that the AI is making good decisions. This way the aim of XAI is to explain what has been done, what is done right now, what will be done next and unveil the information the actions are based on. [7] These characteristics make it possible (i) to confirm existing knowledge (ii) to challenge existing knowledge and (iii) to generate new assumptions. [8]
I for one rue this commandeering of the word "engineering". No, most activities involving stuff are not "engineering". Especially flailing weakly from a distance at an impenetrable tangle of statistical correlations. What a disservice we are doing ourselves.
"Engineers" were originally just eccentric noblemen who liked to tinker around with engines. Kind of an awesome hobby if you think about it, combining clockwork and fire in a cool way. Hence the "eer" suffix implying that they are just really into engines, like a "Mouseketeer" is someone who is really into Mickey Mouse.
It didn't acquire its self-righteously gatekept meaning implying having passed some kind of technical examination to be allowed to draft plans for roads until much later.
A more logged approach with IDK all previous queries in a notebook and their output over time would be more scientific-like and thus closer to "Engineering": https://en.wikipedia.org/wiki/Engineering
> Engineering is the use of scientific principles to design and build machines, structures, and other items, including bridges, tunnels, roads, vehicles, and buildings.[1] The discipline of engineering encompasses a broad range of more specialized fields of engineering, each with a more specific emphasis on particular areas of applied mathematics, applied science, and types of application.
"How and why (NN, LLM, AI,) prompt outputs change over time; with different models, and with different training data" {@type=[schema:Review || schema:ScholarlyArticle], schema:dateModified=}
/? inurl:awesome prompt engineering "llm" site:github.com https://www.google.com/search?q=inurl%3Aawesome+prompt+engin...
XAI: Explainable Artificial Intelligence & epistomology https://en.wikipedia.org/wiki/Explainable_artificial_intelli... :
> Explainable AI (XAI), or Interpretable AI, or Explainable Machine Learning (XML), [1] is artificial intelligence (AI) in which humans can understand the decisions or predictions made by the AI. [2] It contrasts with the "black box" concept in machine learning where even its designers cannot explain why an AI arrived at a specific decision. [3][4] By refining the mental models of users of AI-powered systems and dismantling their misconceptions, XAI promises to help users perform more effectively. [5] XAI may be an implementation of the social _ right to explanation _. [6] XAI is relevant even if there is no legal right or regulatory requirement. For example, XAI can improve the user experience of a product or service by helping end users trust that the AI is making good decisions. This way the aim of XAI is to explain what has been done, what is done right now, what will be done next and unveil the information the actions are based on. [7] These characteristics make it possible (i) to confirm existing knowledge (ii) to challenge existing knowledge and (iii) to generate new assumptions. [8]
Right to explanation: https://en.wikipedia.org/wiki/Right_to_explanation
(Edit; all human)
/? awesome "explainable ai" https://www.google.com/search?q=awesome+%22explainable+ai%22
- (Many other great resources)
- https://github.com/neomatrix369/awesome-ai-ml-dl/blob/master... :
> Post model-creation analysis, ML interpretation/explainability
/? awesome "explainable ai" "XAI" https://www.google.com/search?q=awesome+%22explainable+ai%22...